The histological grading of HCC using fusion images

The histological grading of Hepatocellular Carcinoma is essential to prognosis and treatment planning. Providing a quantitative analysis by machine vision is desired for a determination of the grading result. However, the cells on the biopsy are not all in the some depth of focus under the microscope. Some cells in the images captured by machine may become a blur with a small variance of focus. These cells may not be segmented from images or segmented into a undesized shape and thus affect the grading results. Consequently, an “all-in-focus image” is very useful to the grading of Hepatocellular Carcinoma performed by the machine. In this paper, we proposed an image fusion approach based on the wavelet-based focus measure to fuse two images with different depth of focus into one image, which contains much more in-depth focus cells. In our experiments, we demonstrated that the fused images not only provide clear appearance of cells but also higher accuracy of grading than original images.